A parity-based preprocessing method, which XORs adjacent rows of an image, improves MNIST accuracy by 2 to 6 percent in memristive reservoir computers with a modest device overhead.
Prediction of chaotic time series using recurrent neural networks and reservoir computing techniques: A comparative study,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Preprocessing Methods for Memristive Reservoir Computing for Image Recognition
A parity-based preprocessing method, which XORs adjacent rows of an image, improves MNIST accuracy by 2 to 6 percent in memristive reservoir computers with a modest device overhead.